Advanced

Trust No One: Low Rank Matrix Factorization Using Hierarchical RANSAC

Oskarsson, Magnus LU ; Batstone, Kenneth LU and Åström, Kalle LU (2016) 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), proceedings of p.5820-5829
Abstract
In this paper we present a system for performing low rank matrix factorization. Low-rank matrix factorization is an essential problem in many areas including computer vision, with applications in e.g. affine structure-from-motion, photometric stereo, and non-rigid structure from motion. We specifically target structured data patterns, with outliers and large amounts of missing data. Using recently developed characterizations of minimal solutions to matrix factorization problems with missing data, we show how these can be used as building blocks in a hierarchical system that performs bootstrapping on all levels. This gives an robust and fast system, with state-of-the-art performance.
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
in
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), proceedings of
pages
10 pages
publisher
Computer Vision Foundation
conference name
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
external identifiers
  • Scopus:84986309382
language
English
LU publication?
yes
id
7f903c05-7cc0-4b65-9922-a65dc6f60e68
alternative location
http://www.cv-foundation.org/openaccess/content_cvpr_2016/html/Oskarsson_Trust_No_One_CVPR_2016_paper.html
date added to LUP
2016-09-05 10:28:40
date last changed
2017-01-01 08:33:20
@inproceedings{7f903c05-7cc0-4b65-9922-a65dc6f60e68,
  abstract     = {In this paper we present a system for performing low rank matrix factorization. Low-rank matrix factorization is an essential problem in many areas including computer vision, with applications in e.g. affine structure-from-motion, photometric stereo, and non-rigid structure from motion. We specifically target structured data patterns, with outliers and large amounts of missing data. Using recently developed characterizations of minimal solutions to matrix factorization problems with missing data, we show how these can be used as building blocks in a hierarchical system that performs bootstrapping on all levels. This gives an robust and fast system, with state-of-the-art performance.},
  author       = {Oskarsson, Magnus and Batstone, Kenneth and Åström, Kalle},
  booktitle    = {2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), proceedings of},
  language     = {eng},
  month        = {06},
  pages        = {5820--5829},
  publisher    = {Computer Vision Foundation},
  title        = {Trust No One: Low Rank Matrix Factorization Using Hierarchical RANSAC},
  year         = {2016},
}